© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17715
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare and government benefits

    oai_token-act-pair · gpt-3.5-turbo

    references to welfare and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brun
    -0.72
     Sie
    -0.68
     Ou
    -0.66
     humidity
    -0.62
     Hundred
    -0.61
     Hole
    -0.61
    ergy
    -0.58
     deaf
    -0.57
    gran
    -0.57
     Grind
    -0.56
    POSITIVE LOGITS
    elfare
    1.32
     welfare
    1.15
     entitle
    0.91
    benefit
    0.89
     Welfare
    0.88
     recipients
    0.87
    odynam
    0.82
    odynamics
    0.80
     reform
    0.80
    tarian
    0.76
    Activations Density 0.008%

    No Known Activations